Systems and methods for real-time forecasting and predicting of electrical peaks and managing the energy, health, reliability, and performance of electrical power systems based on an artificial adaptive neural network

• US 9,846,839 B2
• Filed: 10/28/2015
• Issued: 12/19/2017
• Est. Priority Date: 03/10/2006
• Status: Active Grant

• Current Assignee: Power Analytics Corporation (PAC Global, Inc.)
• Original Assignee: Power Analytics Corporation (PAC Global, Inc.)
• Inventors: Nasle, Adib, Nasle, Ali
• Primary Examiner(s): Louis, Andre Pierre
• Application Number:
  US14/925,227
• Publication Number:
  US 20160048757A1
• Time in Patent Office: 783 Days
• Field of Search: 703 13, 703 14, 703 18
• CPC Class Codes: G05B 13/026 using a predictor
• CPC Class Codes: G05B 13/027 using neural networks only
• CPC Class Codes: G05B 15/02 electric
• CPC Class Codes: G05B 19/0428 Safety, monitoring G05B19/0423 takes precedence
• CPC Class Codes: G05B 2219/2639 Energy management, use maximum of cheap power, keep peak load low
• CPC Class Codes: G06F 2111/02 CAD in a network environment, e.g. collaborative CAD or distributed simulation
• CPC Class Codes: G06F 2119/06 Power analysis or power optimisation
• CPC Class Codes: G06F 30/13 Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
• CPC Class Codes: G06F 30/20 Design optimisation, verification or simulation optimisation, verification or simulation of circuit designs G06F30/30
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06N 3/10 Interfaces, programming languages or software development kits, e.g. for simulating neural networks
• CPC Class Codes: G06N 5/048 Fuzzy inferencing
• CPC Class Codes: G06N 7/06 Simulation on general purpose computers

Abstract

A system for utilizing a neural network to make real-time predictions about the health, reliability, and performance of a monitored system are disclosed. The system includes a data acquisition component, a power analytics server and a client terminal. The data acquisition component acquires real-time data output from the electrical system. The power analytics server is comprised of a virtual system modeling engine, an analytics engine, an adaptive prediction engine. The virtual system modeling engine generates predicted data output for the electrical system. The analytics engine monitors real-time data output and predicted data output of the electrical system. The adaptive prediction engine can be configured to forecast an aspect of the monitored system using a neural network algorithm. The adaptive prediction engine is further configured to process the real-time data output and automatically optimize the neural network algorithm by minimizing a measure of error between the real-time data output and an estimated data output predicted by the neural network algorithm.

Claims

1. A system for making real-time forecasts of a monitored system, comprising:

a data acquisition component communicatively connected to a sensor configured to acquire real-time data output from the monitored system;

a power analytics server communicatively connected to the data acquisition component, comprising;

a virtual system modeling engine configured to generate predicted data output for the monitored system utilizing a virtual system model of the monitored system;

an analytics engine configured to monitor the real-time data output and the predicted data output of the monitored system, and update the virtual system model based on the difference between the real-time data output and the predicted data output of the monitored system;

an adaptive prediction engine configured to generate an estimated data output corresponding to the real-time data output based on a neural network algorithm, and minimize a measure of error between the real-time data output and the estimated data output by automatically self-adjusting internal weighting factors of the neural network algorithm, wherein said adjusting includes utilizing a back-propagation algorithm by continually adjusting network weights to minimize a sum-squared error function using the following formulation;

2. The system of claim 1, wherein the analytics engine is further configured to synchronize the real-time data output and the predicted data output of the monitored system.

3. The system of claim 1, wherein the analytics engine is further configured to generate a virtual model calibration request whenever the difference between the real-time data output and the predicted system data falls between a set value and an alarm condition value.

4. The system of claim 1, wherein the analytics engine is further configured to update the virtual system model by adjusting operational parameters of the virtual system model.

5. The system of claim 1, wherein the analytics engine is further configured to generate a real-time report, wherein the real-time report comprises system summary, total and detailed system security and stability, identification of system weaknesses and insure contingency conditions.

6. The system of claim 1, wherein the monitored system is an electrical system.

7. The system of claim 6, wherein the monitored system is a mission critical electrical system.

8. The system of claim 6, wherein the at least one forecasted aspect is related to at least one selected from the group consisting of:

system health and performance;

ability of the electrical system to resist system output variations or deviations from defined tolerance limits of the monitored system;

incorporation of performance and behavioral specifications for all the equipment and components of the electrical system into a real-time management environment;

system reliability and availability;

reliability indices as a function of different system, process and load points;

implementation of different technological solutions to achieve reliability centered maintenance targets and goals;

electrical system capacity levels;

as-designed total power capacity of the electrical system;

ability of the electrical system to maintain availability of its total power capacity;

present utilized power capacity;

electrical system strength and resilience;

dynamic stability predictions across all contingency events;

determination of protection system stress and withstand status; and

determination of system security and stability.

9. The system of claim 1, wherein the measure of error is a sum squared error (SSE) percentage between the estimated data output and the real-time data output.

10. A method for making real-time forecasts of a monitored system, comprising:

receiving real-time data output from one or more sensors interfaced to the monitored system;

generating predicted data output for the one or more sensors interfaced to the monitored system utilizing a virtual system model of the monitored system;

updating the virtual system model of the monitored system when a difference between the real-time data output and the predicted data output exceeds a threshold;

generating an estimated data output corresponding to the real-time data output based on a neural network algorithm;

minimizing a measure of error between the real-time data output and the estimated data output by automatically self-adjusting internal weighting factors of the neural network algorithm,

wherein said adjusting includes utilizing a back-propagation algorithm by continually adjusting network weights to minimize a sum-squared error function using the following formulation;

11. The method of claim 10, further comprising synchronizing the real-time data output and the predicted data output of the monitored system.

12. The method of claim 10, further comprising generating a virtual model calibration request whenever the difference between the real-time data output and the predicted system data falls between a set value and an alarm condition value.

13. The method of claim 10, further comprising updating the virtual system model by adjusting operational parameters of the virtual system model.

14. The method of claim 10, generating and displaying a real-time report of the monitored system, wherein the real-time report comprises system summary, total and detailed system security and stability, identification of system weaknesses and insure contingency conditions.

15. The method of claim 10, wherein the monitored system is an electrical system.

16. The method of claim 15, wherein the monitored system is a mission critical electrical system.

17. The method of claim 15, wherein the at least one forecasted aspect is related to at least one selected from the group consisting of:

system health and performance;

ability of the electrical system to resist system output variations or deviations from defined tolerance limits of the monitored system;

incorporation of performance and behavioral specifications for all the equipment and components of the electrical system into a real-time management environment;

system reliability and availability;

reliability indices as a function of different system, process and load points;

implementation of different technological solutions to achieve reliability centered maintenance targets and goals;

electrical system capacity levels;

as-designed total power capacity of the electrical system;

ability of the electrical system to maintain availability of its total power capacity;

present utilized power capacity;

electrical system strength and resilience;

dynamic stability predictions across all contingency events;

determination of protection system stress and withstand status; and

determination of system security and stability.